vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

gguf : start implementing quantization (WIP)

Browse source
This commit is contained in:
M. Yusuf Sarıgöz 2023-08-12 16:09:47 +03:00
parent fa7c39540c
commit 1fc3d30b71
2 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/gguf/gguf.cpp
View file

@ -421,7 +421,7 @@ int main(int argc, char ** argv) {
GGML_ASSERT(gguf_ex_write(fname) && "failed to write gguf file");
} else if (mode == "r") {
GGML_ASSERT(gguf_ex_read_0(fname) && "failed to read gguf file");
GGML_ASSERT(gguf_ex_read_1(fname) && "failed to read gguf file");
//GGML_ASSERT(gguf_ex_read_1(fname) && "failed to read gguf file");
GGML_ASSERT(gguf_ex_read_2(fname) && "failed to read gguf file");
} else if (mode == "q") {
llama_model_quantize_params params = llama_model_quantize_default_params();